© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 12247
    Prev
    Next
    INDEX
    Explanations

    garden backyard outdoor space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beschreiben
    -0.69
    iders
    -0.69
    Buildings
    -0.68
     المب
    -0.68
     piş
    -0.68
     empêcher
    -0.67
     Buildings
    -0.67
    ckte
    -0.66
    ACING
    -0.66
    унк
    -0.66
    POSITIVE LOGITS
     garden
    3.88
     backyard
    3.77
     yard
    3.48
     gardens
    3.14
    garden
    2.69
     yards
    2.38
     jardín
    2.33
    yard
    2.28
    Garden
    2.23
     courtyard
    2.23
    Activations Density 0.041%

    No Known Activations